Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 759 806 445 784 315 224 526 429 825  76 841 595 880 171 403 473 845 298 251 663
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1] 806 403 663 759 224 595  76 784 526 429 841 315 171 845 880  NA 445  NA 298 251 473 825  NA
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 3 4 4 2 2 5 4 2 5 3
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "d" "v" "a" "p" "o" "Z" "S" "H" "C" "O"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
integer(0)
which( manyNumbersWithNA > 900 )
integer(0)
which( is.na( manyNumbersWithNA ) )
[1] 16 18 23

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
integer(0)
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
integer(0)
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
integer(0)

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "Z" "S" "H" "C" "O"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "d" "v" "a" "p" "o"
manyNumbers %in% 300:600
 [1] FALSE FALSE  TRUE FALSE  TRUE FALSE  TRUE  TRUE FALSE FALSE FALSE  TRUE FALSE FALSE  TRUE  TRUE FALSE
[18] FALSE FALSE FALSE
which( manyNumbers %in% 300:600 )
[1]  3  5  7  8 12 15 16
sum( manyNumbers %in% 300:600 )
[1] 7

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "large" "small" "large" "large" "small" "large" "small" "large" "large" "small" "large" "small" "small"
[14] "large" "large" NA      "small" NA      "small" "small" "small" "large" NA     
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "large"   "small"   "large"   "large"   "small"   "large"   "small"   "large"   "large"   "small"  
[11] "large"   "small"   "small"   "large"   "large"   "UNKNOWN" "small"   "UNKNOWN" "small"   "small"  
[21] "small"   "large"   "UNKNOWN"
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1] 806   0 663 759   0 595   0 784 526   0 841   0   0 845 880  NA   0  NA   0   0   0 825  NA

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 3 4 2 5
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  3  4  2  5
duplicated( duplicatedNumbers )
 [1] FALSE FALSE  TRUE FALSE  TRUE FALSE  TRUE  TRUE  TRUE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 15
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 880
which.min( manyNumbersWithNA )
[1] 7
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 76
range( manyNumbersWithNA, na.rm = TRUE )
[1]  76 880

Sorting/ordering of vectors

manyNumbersWithNA
 [1] 806 403 663 759 224 595  76 784 526 429 841 315 171 845 880  NA 445  NA 298 251 473 825  NA
sort( manyNumbersWithNA )
 [1]  76 171 224 251 298 315 403 429 445 473 526 595 663 759 784 806 825 841 845 880
sort( manyNumbersWithNA, na.last = TRUE )
 [1]  76 171 224 251 298 315 403 429 445 473 526 595 663 759 784 806 825 841 845 880  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 880 845 841 825 806 784 759 663 595 526 473 445 429 403 315 298 251 224 171  76  NA  NA  NA
manyNumbersWithNA[1:5]
[1] 806 403 663 759 224
order( manyNumbersWithNA[1:5] )
[1] 5 2 3 4 1
rank( manyNumbersWithNA[1:5] )
[1] 5 2 3 4 1
sort( mixedLetters )
 [1] "a" "C" "d" "H" "o" "O" "p" "S" "v" "Z"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1]  8.5 10.0  8.5  2.0  4.0  6.0  6.0  2.0  6.0  2.0
rank( manyDuplicates, ties.method = "min" )
 [1]  8 10  8  1  4  5  5  1  5  1
rank( manyDuplicates, ties.method = "random" )
 [1]  9 10  8  3  4  5  6  2  7  1

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.00000000 -0.50000000  0.00000000  0.50000000  1.00000000 -0.15909255 -0.18501522  1.68895313
 [9]  0.50640422  1.94035697 -0.07700514  1.26848332  0.46908529  0.05367367  0.70700205
round( v, 0 )
 [1] -1  0  0  0  1  0  0  2  1  2  0  1  0  0  1
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0 -0.2 -0.2  1.7  0.5  1.9 -0.1  1.3  0.5  0.1  0.7
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00 -0.16 -0.19  1.69  0.51  1.94 -0.08  1.27  0.47  0.05  0.71
floor( v )
 [1] -1 -1  0  0  1 -1 -1  1  0  1 -1  1  0  0  0
ceiling( v )
 [1] -1  0  0  1  1  0  0  2  1  2  0  2  1  1  1

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 x 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2021 Biomedical Data Sciences (BDS) | LUMC